Only for 2.1?

[gigadeplex]

Hi, is this only for SD 2.1, can this be used for 1.5? I guess, I can just switch the clip model, right?

[YuxinWenRick]

Hi, sorry for not including that important detail in the README file, but sure, you can use it for 1.5. SD 1.5 uses the text encoder of CLIP ViT-L/14 from OpenAI, so you can just simply change the argument by: args.clip_model = "ViT-L-14" and args.clip_pretrain = "openai". Also, if you are using the Jupyter notebook, you may also want to change model_id = "runwayml/stable-diffusion-v1-5" when loading the stable diffusion model.

Let me know if you have further questions!

[demirklvc]

Hi, sorry for not including that important detail in the README file, but sure, you can use it for 1.5. SD 1.5 uses the text encoder of CLIP ViT-L/14 from OpenAI, so you can just simply change the argument by: args.clip_model = "ViT-L-14" and args.clip_pretrain = "openai". Also, if you are using the Jupyter notebook, you may also want to change model_id = "runwayml/stable-diffusion-v1-5" when loading the stable diffusion model.

Let me know if you have further questions!

where? in which file?